Fast prediction of indoor airflow distribution inspired by synthetic image generation artificial intelligence

Cary A Faulkner; Dominik S Jankowski; John E Castellini Jr; Wangda Zuo; Philipp Epple; Michael D Sohn; Ali Taleb Zadeh Kasgari; Walid Saad

doi:10.1007/s12273-023-0989-1

Fast prediction of indoor airflow distribution inspired by synthetic image generation artificial intelligence

Build Simul. 2023 Mar 13:1-20. doi: 10.1007/s12273-023-0989-1. Online ahead of print.

Authors

Cary A Faulkner¹, Dominik S Jankowski², John E Castellini Jr¹, Wangda Zuo³, Philipp Epple⁴, Michael D Sohn⁵, Ali Taleb Zadeh Kasgari⁶, Walid Saad⁶

Affiliations

¹ Department of Mechanical Engineering, University of Colorado Boulder, Boulder, CO USA.
² HySON Institut, Sonneberg, Germany.
³ Department of Architectural Engineering, Pennsylvania State University, University Park, PA USA.
⁴ Department of Mechanical Engineering, Coburg University of Applied Sciences, Coburg, Germany.
⁵ Energy Analysis and Environmental Impacts Division, Lawrence Berkeley National Laboratory, Berkeley, CA USA.
⁶ Department of Electrical and Computer Engineering, Virginia Tech, Arlington, VA USA.

Abstract

Prediction of indoor airflow distribution often relies on high-fidelity, computationally intensive computational fluid dynamics (CFD) simulations. Artificial intelligence (AI) models trained by CFD data can be used for fast and accurate prediction of indoor airflow, but current methods have limitations, such as only predicting limited outputs rather than the entire flow field. Furthermore, conventional AI models are not always designed to predict different outputs based on a continuous input range, and instead make predictions for one or a few discrete inputs. This work addresses these gaps using a conditional generative adversarial network (CGAN) model approach, which is inspired by current state-of-the-art AI for synthetic image generation. We create a new Boundary Condition CGAN (BC-CGAN) model by extending the original CGAN model to generate 2D airflow distribution images based on a continuous input parameter, such as a boundary condition. Additionally, we design a novel feature-driven algorithm to strategically generate training data, with the goal of minimizing the amount of computationally expensive data while ensuring training quality of the AI model. The BC-CGAN model is evaluated for two benchmark airflow cases: an isothermal lid-driven cavity flow and a non-isothermal mixed convection flow with a heated box. We also investigate the performance of the BC-CGAN models when training is stopped based on different levels of validation error criteria. The results show that the trained BC-CGAN model can predict the 2D distribution of velocity and temperature with less than 5% relative error and up to about 75,000 times faster when compared to reference CFD simulations. The proposed feature-driven algorithm shows potential for reducing the amount of data and epochs required to train the AI models while maintaining prediction accuracy, particularly when the flow changes non-linearly with respect to an input.

Keywords: artificial intelligence; computational fluid dynamics; conditional generative adversarial network; indoor airflow.